Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633623
Rahul Dey, Christopher Child
Artificial intelligence has become an increasingly important aspect of computer game technology, as designers attempt to deliver engaging experiences for players by creating characters with behavioural realism to match advances in graphics and physics. Recently, behaviour trees have come to the forefront of games AI technology, providing a more intuitive approach than previous techniques such as hierarchical state machines, which often required complex data structures producing poorly structured code when scaled up. The design and creation of behaviour trees, however, requires experience and effort. This research introduces Q-learning behaviour trees (QL-BT), a method for the application of reinforcement learning to behaviour tree design. The technique facilitates AI designers' use of behaviour trees by assisting them in identifying the most appropriate moment to execute each branch of AI logic, as well as providing an implementation that can be used to debug, analyse and optimize early behaviour tree prototypes. Initial experiments demonstrate that behaviour trees produced by the QL-BT algorithm effectively integrate RL, automate tree design, and are human-readable.
{"title":"QL-BT: Enhancing behaviour tree design and implementation with Q-learning","authors":"Rahul Dey, Christopher Child","doi":"10.1109/CIG.2013.6633623","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633623","url":null,"abstract":"Artificial intelligence has become an increasingly important aspect of computer game technology, as designers attempt to deliver engaging experiences for players by creating characters with behavioural realism to match advances in graphics and physics. Recently, behaviour trees have come to the forefront of games AI technology, providing a more intuitive approach than previous techniques such as hierarchical state machines, which often required complex data structures producing poorly structured code when scaled up. The design and creation of behaviour trees, however, requires experience and effort. This research introduces Q-learning behaviour trees (QL-BT), a method for the application of reinforcement learning to behaviour tree design. The technique facilitates AI designers' use of behaviour trees by assisting them in identifying the most appropriate moment to execute each branch of AI logic, as well as providing an implementation that can be used to debug, analyse and optimize early behaviour tree prototypes. Initial experiments demonstrate that behaviour trees produced by the QL-BT algorithm effectively integrate RL, automate tree design, and are human-readable.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114343634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633652
Siming Liu, S. Louis, M. Nicolescu
We investigate using case-injected genetic algorithms to quickly generate high quality unit micro-management in real-time strategy game skirmishes. Good group positioning and movement, which are part of unit micro-management, can help win skirmishes against equal numbers and types of opponent units or win even when outnumbered. In this paper, we use influence maps to generate group positioning and potential fields to guide unit movement and compare the performance of case-injected genetic algorithms, genetic algorithms, and two types of hill-climbing search in finding good unit behaviors for defeating the default Starcraft Brood Wars AI. Early results showed that our hill-climbers were quick but unreliable while the genetic algorithm was slow but reliably found quality solutions a hundred percent of the time. Case-injected genetic algorithms, on the other hand were designed to learn from experience to increase problem solving performance on similar problems. Preliminary results with case-injected genetic algorithms indicate that they find high quality results as reliable as genetic algorithms but up to twice as quickly on related maps.
{"title":"Using CIGAR for finding effective group behaviors in RTS game","authors":"Siming Liu, S. Louis, M. Nicolescu","doi":"10.1109/CIG.2013.6633652","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633652","url":null,"abstract":"We investigate using case-injected genetic algorithms to quickly generate high quality unit micro-management in real-time strategy game skirmishes. Good group positioning and movement, which are part of unit micro-management, can help win skirmishes against equal numbers and types of opponent units or win even when outnumbered. In this paper, we use influence maps to generate group positioning and potential fields to guide unit movement and compare the performance of case-injected genetic algorithms, genetic algorithms, and two types of hill-climbing search in finding good unit behaviors for defeating the default Starcraft Brood Wars AI. Early results showed that our hill-climbers were quick but unreliable while the genetic algorithm was slow but reliably found quality solutions a hundred percent of the time. Case-injected genetic algorithms, on the other hand were designed to learn from experience to increase problem solving performance on similar problems. Preliminary results with case-injected genetic algorithms indicate that they find high quality results as reliable as genetic algorithms but up to twice as quickly on related maps.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128057288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633646
T. Furtak, M. Buro
Perfect information Monte Carlo (PIMC) search is the method of choice for constructing strong Al systems for trick-taking card games. PIMC search evaluates moves in imperfect information games by repeatedly sampling worlds based on state inference and estimating move values by solving the corresponding perfect information scenarios. PIMC search performs well in trick-taking card games despite the fact that it suffers from the strategy fusion problem, whereby the game's information set structure is ignored because moves are evaluated opportunistically in each world. In this paper we describe imperfect information Monte Carlo (IIMC) search, which aims at mitigating this problem by basing move evaluation on more realistic playout sequences rather than perfect information move values. We show that RecPIMC - a recursive IIMC search variant based on perfect information evaluation - performs considerably better than PIMC search in a large class of synthetic imperfect information games and the popular card game of Skat, for which PIMC search is the state-of-the-art cardplay algorithm.
{"title":"Recursive Monte Carlo search for imperfect information games","authors":"T. Furtak, M. Buro","doi":"10.1109/CIG.2013.6633646","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633646","url":null,"abstract":"Perfect information Monte Carlo (PIMC) search is the method of choice for constructing strong Al systems for trick-taking card games. PIMC search evaluates moves in imperfect information games by repeatedly sampling worlds based on state inference and estimating move values by solving the corresponding perfect information scenarios. PIMC search performs well in trick-taking card games despite the fact that it suffers from the strategy fusion problem, whereby the game's information set structure is ignored because moves are evaluated opportunistically in each world. In this paper we describe imperfect information Monte Carlo (IIMC) search, which aims at mitigating this problem by basing move evaluation on more realistic playout sequences rather than perfect information move values. We show that RecPIMC - a recursive IIMC search variant based on perfect information evaluation - performs considerably better than PIMC search in a large class of synthetic imperfect information games and the popular card game of Skat, for which PIMC search is the state-of-the-art cardplay algorithm.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125980690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633640
H. A. Furlong, Ana Luisa Solís González Cosío
Level design is an art which consists of creating the combination of challenge, competition, and interaction that players call fun and involves a careful and deliberate development of the game space. When working with procedural content generation, it is necessary to review how the game designer sets the change in difficulty throughout the different levels. In this paper we present a procedural level generator that can be used for different games and is based on a genetic algorithm. We define a fitness function that does not depend on the game or content type. This function calculates the difference between the difficulty curve defined by the designer and the difficulty curve calculated for the candidate content, so the best content is the one whose difficulty curve best fits the desired curve. To design our generator, we rely on the concept of flow, theories of fun and game design.
{"title":"An approach to level design using procedural content generation and difficulty curves","authors":"H. A. Furlong, Ana Luisa Solís González Cosío","doi":"10.1109/CIG.2013.6633640","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633640","url":null,"abstract":"Level design is an art which consists of creating the combination of challenge, competition, and interaction that players call fun and involves a careful and deliberate development of the game space. When working with procedural content generation, it is necessary to review how the game designer sets the change in difficulty throughout the different levels. In this paper we present a procedural level generator that can be used for different games and is based on a genetic algorithm. We define a fitness function that does not depend on the game or content type. This function calculates the difference between the difficulty curve defined by the designer and the difficulty curve calculated for the candidate content, so the best content is the one whose difficulty curve best fits the desired curve. To design our generator, we rely on the concept of flow, theories of fun and game design.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125518690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633626
Matthias Kuchem, Mike Preuss, Günter Rudolph
Modern realtime strategy (RTS) games as Star-Craft 2 educe so-called metagames in which the players compete for the best strategies. The metagames of complex RTS games thrive in the absence of apparent dominant strategies, and developers will intervene to adjust the game when such strategies arise in public. However, there are still strategies considered as strong and ones thought of as weak. For the Zerg faction in StarCraft 2, we show how strong strategies can be identified by taking combat strength and economic power into account. The multi-objective perspective enables us to clearly rule out the unfavourable ones of the single optimal build orders and thus selects interesting openings to be tested by real players. By this means, we are e.g. able to explain the success of the recently proposed 7-roach opening. While we demonstrate our approach for StarCraft 2 only, it is of course applicable to other RTS games, given build-order optimization tools exist.
{"title":"Multi-objective assessment of pre-optimized build orders exemplified for StarCraft 2","authors":"Matthias Kuchem, Mike Preuss, Günter Rudolph","doi":"10.1109/CIG.2013.6633626","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633626","url":null,"abstract":"Modern realtime strategy (RTS) games as Star-Craft 2 educe so-called metagames in which the players compete for the best strategies. The metagames of complex RTS games thrive in the absence of apparent dominant strategies, and developers will intervene to adjust the game when such strategies arise in public. However, there are still strategies considered as strong and ones thought of as weak. For the Zerg faction in StarCraft 2, we show how strong strategies can be identified by taking combat strength and economic power into account. The multi-objective perspective enables us to clearly rule out the unfavourable ones of the single optimal build orders and thus selects interesting openings to be tested by real players. By this means, we are e.g. able to explain the success of the recently proposed 7-roach opening. While we demonstrate our approach for StarCraft 2 only, it is of course applicable to other RTS games, given build-order optimization tools exist.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128162460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633630
Hendrik Baier, M. Winands
Monte-Carlo Tree Search is a sampling-based search algorithm that has been successfully applied to a variety of games. Monte-Carlo rollouts allow it to take distant consequences of moves into account, giving it a strategic advantage in many domains over traditional depth-limited minimax search with alpha-beta pruning. However, MCTS builds a highly selective tree and can therefore miss crucial moves and fall into traps in tactical situations. Full-width minimax search does not suffer from this weakness. This paper proposes MCTS-minimax hybrids that employ shallow minimax searches within the MCTS framework. The three proposed approaches use minimax in the selection/expansion phase, the rollout phase, and the backpropagation phase of MCTS. Without requiring domain knowledge in the form of evaluation functions, these hybrid algorithms are a first step at combining the strategic strength of MCTS and the tactical strength of minimax. We investigate their effectiveness in the test domains of Connect-4 and Breakthrough.
{"title":"Monte-Carlo Tree Search and minimax hybrids","authors":"Hendrik Baier, M. Winands","doi":"10.1109/CIG.2013.6633630","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633630","url":null,"abstract":"Monte-Carlo Tree Search is a sampling-based search algorithm that has been successfully applied to a variety of games. Monte-Carlo rollouts allow it to take distant consequences of moves into account, giving it a strategic advantage in many domains over traditional depth-limited minimax search with alpha-beta pruning. However, MCTS builds a highly selective tree and can therefore miss crucial moves and fall into traps in tactical situations. Full-width minimax search does not suffer from this weakness. This paper proposes MCTS-minimax hybrids that employ shallow minimax searches within the MCTS framework. The three proposed approaches use minimax in the selection/expansion phase, the rollout phase, and the backpropagation phase of MCTS. Without requiring domain knowledge in the form of evaluation functions, these hybrid algorithms are a first step at combining the strategic strength of MCTS and the tactical strength of minimax. We investigate their effectiveness in the test domains of Connect-4 and Breakthrough.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122550607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633664
N.St.J.F. Bowen, Jonathan Todd, G. Sukthankar
Constructing an effective real-time strategy bot requires multiple interlocking elements including a well-designed architecture, efficient build order, and good strategic and tactical decision-making. However even when the bot's high-level strategy and resource allocation is sound, poor battlefield tactics can result in unnecessary losses. This paper focuses on the problem of avoiding troop loss by identifying good tactical groupings. Banding separated units together using UCT (Upper Confidence bounds applied to Trees) along with a learned reward model outperforms grouping heuristics at winning battles while preserving resources. This paper describes our findings in the context of the Adjutant bot design which won the best Newcomer honor at CIG 2012 and is the basis for our 2013 entry.
{"title":"Adjutant bot: An evaluation of unit micromanagement tactics","authors":"N.St.J.F. Bowen, Jonathan Todd, G. Sukthankar","doi":"10.1109/CIG.2013.6633664","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633664","url":null,"abstract":"Constructing an effective real-time strategy bot requires multiple interlocking elements including a well-designed architecture, efficient build order, and good strategic and tactical decision-making. However even when the bot's high-level strategy and resource allocation is sound, poor battlefield tactics can result in unnecessary losses. This paper focuses on the problem of avoiding troop loss by identifying good tactical groupings. Banding separated units together using UCT (Upper Confidence bounds applied to Trees) along with a learned reward model outperforms grouping heuristics at winning battles while preserving resources. This paper describes our findings in the context of the Adjutant bot design which won the best Newcomer honor at CIG 2012 and is the basis for our 2013 entry.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116145602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633665
Hyun-Soo Park, Kyung-Joong Kim
What's the most important sources of information to guess the internal strategy of your opponents? The best way is to play games against them and infer their strategy from the experience. For novice players, they should play lot of games to identify other's strategy successfully. However, experienced players usually play small number of games to model other's strategy. The secret is that they intelligently design their plays to maximize the chance of discovering the most uncertain parts. Similarly, in this paper, we propose to use an incremental active learning for modeling opponents. It refines the other's models incrementally by cycling “estimation (inference)“ and “exploration (playing games)” steps. Experimental results with Iterative Prisoner's Dilemma games show that the proposed method can reveal other's strategy successfully.
{"title":"Opponent modeling with incremental active learning: A case study of Iterative Prisoner's Dilemma","authors":"Hyun-Soo Park, Kyung-Joong Kim","doi":"10.1109/CIG.2013.6633665","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633665","url":null,"abstract":"What's the most important sources of information to guess the internal strategy of your opponents? The best way is to play games against them and infer their strategy from the experience. For novice players, they should play lot of games to identify other's strategy successfully. However, experienced players usually play small number of games to model other's strategy. The secret is that they intelligently design their plays to maximize the chance of discovering the most uncertain parts. Similarly, in this paper, we propose to use an incremental active learning for modeling opponents. It refines the other's models incrementally by cycling “estimation (inference)“ and “exploration (playing games)” steps. Experimental results with Iterative Prisoner's Dilemma games show that the proposed method can reveal other's strategy successfully.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125046844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633661
Samuel Maycock, Tommy Thompson
This short paper highlights an investigation into the application of A* search to facilitate forms of input for games on touchscreen mobile devices. We focus this work specifically on navigation games such as Ms Pac-Man. This project proposes two alternative methods for touch-control that utilise A* pathfinding for navigation purposes - a touch to destination and a `sweep' input. We then assess whether these methods lead to improved performance and user experience through human participation.
{"title":"Enhancing touch-driven navigation using informed search in Ms. Pac-Man","authors":"Samuel Maycock, Tommy Thompson","doi":"10.1109/CIG.2013.6633661","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633661","url":null,"abstract":"This short paper highlights an investigation into the application of A* search to facilitate forms of input for games on touchscreen mobile devices. We focus this work specifically on navigation games such as Ms Pac-Man. This project proposes two alternative methods for touch-control that utilise A* pathfinding for navigation purposes - a touch to destination and a `sweep' input. We then assess whether these methods lead to improved performance and user experience through human participation.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131512980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-17DOI: 10.1109/CIG.2013.6633653
Kenneth W. Regan, Tamal Biswas
We build a model for the kind of decision making involved in games of strategy such as chess, making it abstract enough to remove essentially all game-specific contingency, and compare it to known psychometric models of test taking, item response, and performance assessment. Decisions are modeled in terms of fallible agents Z faced with possible actions ai whose utilities Ui=U (ai) are not fully apparent. The three main goals of the model are prediction, meaning to infer probabilities Pi for Z to choose ai; intrinsic rating, meaning to assess the skill of a person's actual choices ait over various test items t; and simulation of the distribution of choices by an agent with a specified skill set. We describe and train the model on large data from chess tournament games of different ranks of players, and exemplify its accuracy by applying it to give intrinsic ratings for world championship matches.
{"title":"Psychometric modeling of decision making via game play","authors":"Kenneth W. Regan, Tamal Biswas","doi":"10.1109/CIG.2013.6633653","DOIUrl":"https://doi.org/10.1109/CIG.2013.6633653","url":null,"abstract":"We build a model for the kind of decision making involved in games of strategy such as chess, making it abstract enough to remove essentially all game-specific contingency, and compare it to known psychometric models of test taking, item response, and performance assessment. Decisions are modeled in terms of fallible agents Z faced with possible actions ai whose utilities Ui=U (ai) are not fully apparent. The three main goals of the model are prediction, meaning to infer probabilities Pi for Z to choose ai; intrinsic rating, meaning to assess the skill of a person's actual choices ait over various test items t; and simulation of the distribution of choices by an agent with a specified skill set. We describe and train the model on large data from chess tournament games of different ranks of players, and exemplify its accuracy by applying it to give intrinsic ratings for world championship matches.","PeriodicalId":158902,"journal":{"name":"2013 IEEE Conference on Computational Inteligence in Games (CIG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134014887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：